mlfoundations-dev/s1K-sharegpt_1743202401_eval_0771
收藏Hugging Face2025-03-29 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/s1K-sharegpt_1743202401_eval_0771
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含预计算模型输出结果的评估数据集，用于评估模型在AIME24、AIME25和MATH500三个指标上的表现。AIME24和AIME25详细记录了每次运行的准确率和问题解决情况，MATH500则提供了整体的准确率和问题解决情况。
This is an evaluation dataset containing precomputed model outputs, used to assess the models performance on three metrics: AIME24, AIME25, and MATH500. AIME24 and AIME25 provide detailed records of accuracy and question-solving in each run, while MATH500 offers overall accuracy and question-solving statistics.
提供机构：
mlfoundations-dev
